CN115455791B - Method for improving landslide displacement prediction accuracy based on numerical simulation technology - Google Patents
Method for improving landslide displacement prediction accuracy based on numerical simulation technology Download PDFInfo
- Publication number
- CN115455791B CN115455791B CN202211242391.9A CN202211242391A CN115455791B CN 115455791 B CN115455791 B CN 115455791B CN 202211242391 A CN202211242391 A CN 202211242391A CN 115455791 B CN115455791 B CN 115455791B
- Authority
- CN
- China
- Prior art keywords
- time sequence
- landslide
- displacement
- similarity
- numerical simulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000006073 displacement reaction Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004088 simulation Methods 0.000 title claims abstract description 41
- 238000005516 engineering process Methods 0.000 title claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims abstract description 100
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 30
- 230000006870 function Effects 0.000 claims abstract description 9
- 230000035699 permeability Effects 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000010801 machine learning Methods 0.000 claims description 20
- 239000002689 soil Substances 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 239000013598 vector Substances 0.000 claims description 6
- 239000003673 groundwater Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 239000011435 rock Substances 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011439 discrete element method Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000003068 static effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/12—Timing analysis or timing optimisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Pit Excavations, Shoring, Fill Or Stabilisation Of Slopes (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to the field of landslide displacement prediction methods, in particular to a method for improving landslide displacement prediction accuracy based on a numerical simulation technology, which comprises the following steps: obtaining geological condition parameters, physical and mechanical parameters, soil-water characteristic curves, permeability coefficient functions and historical monitoring data of a target landslide hidden danger point; preprocessing historical monitoring data to obtain a time sequence of actual monitoring data; establishing a numerical analysis model of a potential point of the objective landslide; fitting calculation is carried out to obtain time sequence data of water level, earth surface displacement, deep displacement and stress corresponding to the actual monitoring position on the hidden trouble point of the target landslide; performing similarity analysis and accuracy analysis on the two groups of obtained time sequences; judging whether the similarity analysis and the accuracy analysis meet the preset requirements, if so, predicting landslide displacement, and if not, debugging according to the difference of the two time sequences until the preset requirements are met. The method and the device improve the accuracy of landslide displacement prediction.
Description
Technical Field
The invention relates to the field of landslide displacement prediction methods, in particular to a method for improving landslide displacement prediction accuracy based on a numerical simulation technology.
Background
Landslide is a natural geological disaster with serious hazard, and the number of times of occurrence of the disaster landslide every year is more, so that economic loss exceeds 10 hundred million yuan, and the life and property safety of people is seriously influenced, so that the establishment of a landslide disaster early warning system has important significance.
The displacement prediction is an important content in landslide hazard early warning, a static prediction model is commonly used for the displacement prediction of landslide, and the prediction effect of the static prediction model is poor because the landslide deformation is a complex nonlinear dynamic process. For this, with the rise of artificial intelligence technology, the prediction effect can be improved to a certain extent based on the landslide displacement prediction of machine learning, but when the landslide displacement is predicted by utilizing a machine learning algorithm, the prediction accuracy is highly dependent on the historical monitoring data quality of the landslide displacement, and for the data-driven landslide displacement prediction method based on the machine learning to predict the landslide displacement, the quantity and quality of the landslide displacement historical monitoring data used for a machine learning algorithm training model directly influence the accuracy of landslide displacement prediction.
The original data amount for predicting landslide displacement by machine learning is less due to the fact that on-site monitoring instruments of landslide engineering are limited, the data acquisition frequency of the monitoring instruments is limited, the installation time of the monitoring instruments is often after the landslide is greatly deformed, and the like; meanwhile, due to the reasons of equipment stability, equipment storage or transmission faults, extremely bad weather and the like, the probability of data missing and data abnormality of original monitoring data is extremely high, and the quality of the original data for predicting landslide displacement by machine learning is poor, so that the accuracy of a prediction result of the landslide displacement by machine learning is poor.
Disclosure of Invention
The invention aims to provide a method for improving landslide displacement prediction accuracy based on a numerical simulation technology, so as to solve the problem of poor accuracy of a prediction result of landslide displacement prediction by existing machine learning.
The method for improving the landslide displacement prediction accuracy based on the numerical simulation technology in the scheme comprises the following steps:
step 1, obtaining geological condition parameters of a potential point of a target landslide;
step 2, obtaining physical and mechanical parameters, a soil-water characteristic curve and a permeability coefficient function of a rock-soil body of a potential point of the objective landslide;
step 3, acquiring historical monitoring data of the characteristic spatial distribution characteristics of potential points of the objective landslide;
step 4, preprocessing the historical monitoring data in the step 3 to obtain a time sequence of actual monitoring data of surface displacement monitoring, deep displacement monitoring, groundwater level monitoring and stress monitoring of the hidden trouble point of the target landslide;
step 5, establishing a numerical analysis model of the target landslide hidden danger point based on a numerical simulation means by utilizing the geological condition parameters of the target landslide hidden danger point obtained in the step 1 and the step 2, the physical and mechanical parameters of the key rock and soil layers, the soil-water characteristic curve and the permeability coefficient function;
step 6, working condition information of a target landslide hidden danger point is obtained, and boundary conditions of a landslide numerical simulation process are set according to the working condition information to carry out numerical analysis and calculation, so that time sequence data of water level, earth surface displacement, deep displacement and stress corresponding to an actual monitoring position on the target landslide hidden danger point are obtained;
step 7, carrying out time sequence similarity analysis and accuracy analysis on the time sequence data of the water level, the earth surface displacement, the deep displacement and the stress obtained in the step 6 and the time sequence of the history monitoring data of the target landslide hidden danger point after pretreatment in the step 4;
step 8, if the time sequence similarity and accuracy in the step 7 meet the preset requirements, predicting landslide displacement by using the time sequence data of water level, surface displacement, deep displacement and stress obtained by the numerical simulation in the step 6 as machine learning training data;
and 9, if the similarity and accuracy of the time sequence in the step 7 do not meet the preset requirements, debugging the parameters of the numerical simulation model in the step 6 according to the difference between the time sequence obtained based on numerical simulation in the step 6 and the time sequence of the actual monitoring data corresponding to the hidden danger point of the target landslide in the step 4, and re-executing the step 6 and the step 7 until the similarity and accuracy of the time sequence in the step 7 meet the preset requirements, and executing the step 8.
The beneficial effect of this scheme is:
based on geological background conditions of the target landslide hidden danger points, physical and mechanical parameters of a rock-soil body, a soil-water characteristic curve and a permeability coefficient function, carrying out numerical modeling and calculation on the target landslide hidden danger points to obtain simulation monitoring data with high similarity and accuracy of a time sequence of actual monitoring data of the target landslide hidden danger points, encrypting the time monitoring data of the target landslide hidden danger points and repairing missing data are realized on a physical mechanism, data noise caused by on-site sensor errors and the like is reduced, and therefore the quantity and quality of the data are greatly improved.
The simulation monitoring data with higher time sequence similarity and accuracy with the actual monitoring data of the hidden danger point of the target landslide is used as the training data of the machine learning algorithm in landslide displacement prediction, so that the problem that the accuracy of displacement prediction is low due to the fact that the training data is small in data quantity, poor in quality and the like when the original field monitoring data of the hidden danger point of the target landslide is directly used as the training data of the machine learning algorithm in landslide displacement prediction can be effectively solved, and the accuracy of landslide displacement prediction is improved.
Further, in the step 3, the historical monitoring data includes surface displacement monitoring, deep displacement monitoring, groundwater level monitoring, stress monitoring, and monitoring positions and depths thereof at the hidden trouble points of the objective landslide.
The beneficial effects are that: the various historical monitoring data can accurately and completely represent landslide evolution conditions.
In step 5, the numerical simulation means is one of a finite element method, a discrete element method and an object point method.
The beneficial effects are that: the application range of a plurality of different numerical simulation means is wider.
Further, in the step 6, the working condition information includes rainfall, reservoir water level change and earthquake, and the collection frequency and time span of the time series data are the same as the actual monitoring data of the hidden trouble point of the objective landslide in the step 4.
The beneficial effects are that: the time sequence of the numerical simulation fitting keeps consistent with the actual monitoring data of the hidden danger point of the target landslide in the step 4 in the acquisition frequency and the time span, and the data format can be ensured to be the same when the similarity and the accuracy of the data are analyzed in the step 7.
Further, in the step 7, the similarity analysis includes numerical similarity and directional similarity, and the accuracy analysis includes a dynamic time warping distance.
The beneficial effects are that: the numerical similarity can be used for representing the similarity degree of the two time sequences in numerical value, representing how far apart each point of the two sequences is on a two-dimensional plane, judging the ascending or descending trend of the two sequences through the direction similarity, and accurately analyzing the problems possibly caused by time sequence deviation and inconsistent time sequence length.
Further, in the step 7, the numerical similarity analysis includes, assuming that the time series obtained in the step 6 and the time series monitored in the step 4 are respectively represented as p= (x) 1 ,x 2 ,...,x n ) And q= (y) 1 ,y 2 ,...,y n ) And calculating the Euclidean distance between the time sequence P and the time sequence Q, and carrying out similarity analysis on the time sequence P and the time sequence Q according to the Euclidean distance, wherein the Euclidean distance is expressed as:
the direction similarity analysis comprises the steps of projecting points on a time sequence P and a time sequence Q in a plane coordinate system, taking a line between each point on a curve formed by the time sequence P and the time sequence Q and an origin of a coordinate axis as a vector, calculating cosine of an included angle of the two vectors to be used for representing cosine similarity, calculating average cosine similarity of the time sequence P and the time sequence Q, and carrying out the direction similarity analysis of the time sequence P and the time sequence Q according to the average cosine similarity, wherein the cosine similarity is expressed as follows:
the beneficial effects are that: and the Euclidean distance and cosine similarity are calculated for the two sequences, so that the similarity degree of the two time sequences is quantitatively identified, and the intuitiveness and accuracy of similarity degree judgment are improved.
Further, in the step 7, the dynamic time warping distance analysis includes, assuming that the time series P obtained in the step 6 and the time series Q monitored in the step 4 are represented as p= (x), respectively 1 ,x 2 ,...,x m ) And q= (y) 1 ,y 2 ,...,y n ) The distance matrix between two time series is expressed as A m×n ＝(a ij ) m×n Wherein a is ij Calculating by adopting Euclidean distance;
let the dynamic time-planned path be w= (W) 1 ,w 2 ,...,w n ) Calculating the DTW distance of the time sequence P obtained in the step 6 and the time sequence Q obtained in the step 4, and carrying out similarity analysis according to the DTW distance, wherein the DTW distance is expressed as:
the beneficial effects are that: through dynamic time warping distance analysis, the relation of the two time sequences on the integral difference is conveniently and accurately described and judged, so that the offset difference between the two time sequences is accurately determined.
Further, in the step 8, the preset requirement is to meet the numerical similarity requirement, the direction similarity requirement and the DTW similarity requirement simultaneously;
let the actual monitoring data range be R, the said predetermined requirement is: if index S DE Satisfy S DE ＝D E R is less than or equal to 10 percent, and the time sequence P obtained in the step 6 and the time sequence Q obtained in the step 4 meet the numerical similarity requirement; a determination coefficient (R is set for the time series curve of the actual monitoring data 2 ) A fitting curve larger than 0.98, calculating the DTW distance DTW between the time sequence Q of the actual monitoring data and the fitting curve 1 Calculating the DTW distance DTW between the time sequence P of the actual monitoring data and the time sequence P in the step 6 2 If the DTW is satisfied 2 ≤DTW 1 And (3) the time sequence P obtained in the step (6) and the time sequence Q obtained in the step (4) meet the DWT similarity requirement.
The beneficial effects are that: the preset requirements are set to meet the numerical similarity requirement, the direction similarity requirement and the DTW similarity requirement simultaneously, whether the time sequence obtained through the fitting mode is similar to the actual time sequence or not can be judged, whether the fitted time sequence accords with the actual situation or not is further determined, and the accuracy of the follow-up prediction result is improved.
In step 8, the time series data of the monitoring data of the water level, the earth surface displacement, the deep displacement and the stress are increased in acquisition frequency according to the requirement of the landslide machine learning prediction model.
The beneficial effects are that: by increasing the acquisition frequency, the amount of data for machine learning training data in step 8 can be increased.
In step 8, the time span for monitoring data acquisition of water level, ground surface displacement, deep displacement and stress is increased according to the target landslide potential displacement prediction.
The beneficial effects are that: by increasing the time span over which data is acquired, the data coverage can be improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for improving landslide displacement prediction accuracy based on numerical simulation technology.
Detailed Description
Further details are provided below with reference to the specific embodiments.
Examples
As shown in fig. 1, the method for improving landslide displacement prediction accuracy based on a numerical simulation technology comprises the following steps:
step 1, obtaining geological condition parameters of a target landslide hidden trouble point, wherein the geological condition parameters are obtained from obtained investigation data, and include stratum sequence, lithology characteristics, contact relation, stratum occurrence, structural surface distribution and combination characteristics and hydrologic information.
And 2, acquiring physical and mechanical parameters, a soil-water characteristic curve and a permeability coefficient function of a rock-soil body of the potential point of the objective landslide based on a field test and an indoor test, wherein the field test and the indoor test are performed in an existing mode, and the description is omitted.
And 3, acquiring historical monitoring data of the characteristic spatial distribution characteristics of the potential points of the target landslide according to the on-site monitoring data of the potential points of the target landslide, wherein the on-site monitoring data can be obtained by storing the sensor and monitoring equipment in the early monitoring process, and the historical monitoring data comprises surface displacement monitoring, deep displacement monitoring, underground water level monitoring, stress monitoring and monitoring positions and depths of the sensor and the monitoring equipment at the potential points of the target landslide.
And 4, preprocessing the historical monitoring data in the step 3 to obtain the time sequence of actual monitoring data of surface displacement monitoring, deep displacement monitoring, groundwater level monitoring and stress monitoring of the potential points of the target landslide, wherein the preprocessing comprises the steps of removing data noise and deleting abnormal data columns so as to remove abnormal data with obvious logic errors.
And 5, establishing a numerical analysis model of the target landslide hidden danger point 1:1 based on a numerical simulation means by utilizing the geological condition parameters of the target landslide hidden danger point obtained in the step 1 and the step 2, the physical and mechanical parameters of the key rock and soil layer, the soil and water characteristic curve and the permeability coefficient function, wherein the numerical simulation means is one of a finite element, a discrete element and an object particle method.
And 6, acquiring working condition information of the potential points of the target landslide, wherein the working condition information comprises rainfall, reservoir water level change and earthquake, and carrying out numerical analysis calculation according to boundary conditions of a landslide numerical simulation process set on the basis of the numerical analysis model established in the step 5, wherein the boundary conditions are the hydraulic boundary conditions corresponding to the rainfall and reservoir water level change and the earthquake boundary conditions, so as to obtain time series data of water level, earth surface displacement, deep displacement and stress corresponding to the actual monitoring positions on the potential points of the target landslide, and the acquisition frequency and time span of the time series data are the same as those of the actual monitoring data of the potential points of the target landslide in the step 4.
And 7, carrying out time sequence similarity analysis and accuracy analysis on the time sequence data of the water level, the earth surface displacement, the deep displacement and the stress obtained in the step 6 and the time sequence of the history monitoring data after pretreatment in the step 4. The similarity analysis includes numerical similarity and directional similarity, and the accuracy analysis includes dynamic time warping distance.
Numerical similarity means how similar two time series are in value, i.e. how far apart each point of the two series is in the two-dimensional plane. The numerical similarity analysis includes, assuming that the time series obtained in step 6 and the time series monitored in step 4 are respectively expressed as p= (x) 1 ,x 2 ,...,x n ) And q= (y) 1 ,y 2 ,...,y n ) Calculating Euclidean distance between the time sequence P and the time sequence Q, analyzing the numerical similarity between the time sequence P and the time sequence Q according to the Euclidean distance, and if the Euclidean distance is smaller, namely the preset requirement of the Euclidean distance is not higher than 10%, if the index S DE Satisfy S DE ＝D E R is less than or equal to 10 percent, and represents that the time sequences in the step 6 and the step 4 are similar in value, namely the numerical similarity degree of the time sequences can be judged, and the Euclidean distance is expressed as follows:
the directional similarity can mean that two time series curves should have similar rising or falling trends at the same time. The direction similarity analysis comprises the steps of projecting points on a time sequence P and a time sequence Q in a plane coordinate system, taking a line between each point on a curve formed by the time sequence P and the time sequence Q and an origin of a coordinate axis as a vector, calculating cosine of an included angle of the two vectors to represent cosine similarity, calculating average cosine similarity of the time sequence P and the time sequence Q, carrying out the direction similarity analysis of the time sequence P and the time sequence Q according to the average cosine similarity, and when the cosine value is closer to 1, indicating that the cosine similarity between the time sequence P and the time sequence Q is higher, the cosine similarity is more consistent in the direction, and the cosine similarity is expressed as:
the dynamic time warping distance analysis includes, assuming that the time series P obtained in step 6 and the time series Q monitored in step 4 are represented as p= (x) 1 ,x 2 ,...,x m ) And q= (y) 1 ,y 2 ,...,y n ) Wherein m and n may be equal and m and n may be unequal, the distance matrix between the two time series is denoted as A m×n ＝(a ij ) m×n Wherein a is ij Calculating by adopting Euclidean distance;
let the dynamic time-planned path be w= (W) 1 ,w 2 ,...,w n ) Calculating the DTW distance of the time sequence P obtained in the step 6 and the time sequence Q obtained in the step 4, carrying out similarity analysis according to the DTW distance, wherein the smaller the DTW distance is, the higher the similarity between the time sequence P and the time sequence Q is, and the DTW distance is expressed as:
and 8, if the time sequence similarity and accuracy in the step 7 meet the preset requirements, predicting landslide displacement by using the time sequence data of water level, surface displacement, deep displacement and stress obtained by the numerical simulation in the step 6 as machine learning training data.
The preset requirements are to simultaneously meet the numerical similarity requirements, the direction similarity requirements and the DTW similarity requirements.
Let the actual monitoring data range be R, the said predetermined requirement is: if index S DE Satisfy S DE ＝D E R is less than or equal to 10 percent, and the time sequence P obtained in the step 6 and the time sequence Q obtained in the step 4 meet the numerical similarity requirement; a determination coefficient (R is set for the time series curve of the actual monitoring data 2 ) A fitting curve larger than 0.98, calculating the DTW distance DTW between the time sequence Q of the actual monitoring data and the fitting curve 1 Calculating the DTW distance DTW between the time sequence P of the actual monitoring data and the time sequence P in the step 6 2 If the DTW is satisfied 2 ≤DTW 1 And (3) the time sequence P obtained in the step (6) and the time sequence Q obtained in the step (4) meet the DWT similarity requirement.
And increasing the acquisition frequency according to the needs of the landslide machine learning prediction model by using time series data of monitoring data of water level, earth surface displacement, deep displacement and stress. And according to the displacement prediction of the hidden danger of the target landslide, the time span of monitoring data acquisition of water level, earth surface displacement, deep displacement and stress is required to be increased.
And 9, if the similarity and accuracy of the time sequence in the step 7 do not meet the preset requirements, debugging the numerical simulation model parameters in the step 6 according to the difference between the time sequence obtained based on numerical simulation in the step 6 and the time sequence of the actual monitoring data corresponding to the target landslide hidden danger point in the step 4, wherein the debugging is the process of taking values, calculating, checking and fine tuning in the distribution interval of the physical and mechanical parameters of the rock and soil body, and re-executing the step 6 and the step 7 until the similarity and accuracy of the time sequence in the step 7 meet the preset requirements, and executing the step 8.
Compared with the existing static prediction model and machine learning landslide displacement prediction, aiming at the problems of small data quantity and poor quality and affecting prediction accuracy, the method is generally carried out by improving the performance of data acquisition equipment and increasing the acquisition quantity or acquisition frequency of the data quantity, the embodiment does not simply increase the data quantity or simply improve the monitoring effect of a monitoring end, but carries out numerical modeling and calculation on the target landslide hidden danger point based on the geological background condition of the target landslide hidden danger point, the physical and mechanical parameters of a rock-soil body, the characteristic curve of soil and water and the permeability coefficient function to obtain the analog monitoring data with higher similarity and accuracy of the time sequence of the actual monitoring data of the target landslide hidden danger point, thereby realizing the density increase of the time monitoring data of the target landslide hidden danger point and the repair of the missing data and reducing the data noise caused by the reasons of errors of a field sensor and the like, thereby greatly improving the data quantity and quality. The simulation monitoring data with higher time sequence similarity and accuracy with the actual monitoring data of the hidden danger point of the target landslide is used as the training data of the machine learning algorithm in landslide displacement prediction, so that the problem that the accuracy of displacement prediction is low due to the fact that the training data is small in data quantity, poor in quality and the like when the original field monitoring data of the hidden danger point of the target landslide is directly used as the training data of the machine learning algorithm in landslide displacement prediction can be effectively solved, and the accuracy of landslide displacement prediction is improved.
The foregoing is merely exemplary embodiments of the present invention, and specific structures and features that are well known in the art are not described in detail herein. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these should also be considered as the scope of the present invention, which does not affect the effect of the implementation of the present invention and the utility of the patent. The protection scope of the present application shall be subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (10)
1. The method for improving the landslide displacement prediction accuracy based on the numerical simulation technology is characterized by comprising the following steps of:
step 1, obtaining geological condition parameters of a potential point of a target landslide;
step 2, obtaining physical and mechanical parameters, a soil-water characteristic curve and a permeability coefficient function of a rock-soil body of a potential point of the objective landslide;
step 3, acquiring historical monitoring data of the characteristic spatial distribution characteristics of potential points of the objective landslide;
step 4, preprocessing the historical monitoring data in the step 3, removing abnormal data with obvious logic errors, and obtaining a time sequence of actual monitoring data of surface displacement monitoring, deep displacement monitoring, groundwater level monitoring and stress monitoring of the potential points of the objective landslide;
step 5, establishing a numerical analysis model of the target landslide hidden danger point based on a numerical simulation means by utilizing the geological condition parameters of the target landslide hidden danger point obtained in the step 1 and the step 2, the physical and mechanical parameters of the key rock and soil layers, the soil-water characteristic curve and the permeability coefficient function;
step 6, working condition information of a target landslide hidden danger point is obtained, and boundary conditions of a landslide numerical simulation process are set according to the working condition information to carry out numerical analysis and calculation, so that time sequence data of water level, earth surface displacement, deep displacement and stress corresponding to an actual monitoring position on the target landslide hidden danger point are obtained;
step 7, carrying out time sequence similarity analysis and accuracy analysis on the time sequence data of the water level, the earth surface displacement, the deep displacement and the stress obtained in the step 6 and the time sequence of the history monitoring data of the target landslide hidden danger point after pretreatment in the step 4;
step 8, if the time sequence similarity and accuracy in the step 7 meet the preset requirements, predicting landslide displacement by using the time sequence data of water level, surface displacement, deep displacement and stress obtained by the numerical simulation in the step 6 as machine learning training data;
and 9, if the similarity and accuracy of the time sequence in the step 7 do not meet the preset requirements, debugging the parameters of the numerical simulation model in the step 6 according to the difference between the time sequence obtained based on numerical simulation in the step 6 and the time sequence of the actual monitoring data corresponding to the hidden danger point of the target landslide in the step 4, and re-executing the step 6 and the step 7 until the similarity and accuracy of the time sequence in the step 7 meet the preset requirements, and executing the step 8.
2. The method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 1, wherein the method comprises the following steps: in the step 3, the history monitoring data includes surface displacement monitoring, deep displacement monitoring, ground water level monitoring, stress monitoring and monitoring positions and depths thereof at hidden trouble points of the target landslide.
3. The method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 2, wherein the method comprises the following steps: in the step 5, the numerical simulation means is one of a finite element method, a discrete element method and an object point method.
4. The method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 3, wherein the method comprises the following steps: in the step 6, the working condition information comprises rainfall, reservoir water level change and earthquake, and the acquisition frequency and time span of the time series data are the same as the actual monitoring data of the hidden danger point of the target landslide in the step 4.
5. The method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 4, wherein the method comprises the following steps: in the step 7, the similarity analysis includes numerical similarity and directional similarity, and the accuracy analysis includes a dynamic time warping distance.
6. The method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 5, wherein the method comprises the following steps: in the step 7, the numerical similarity analysis includes, assuming that the time series obtained in the step 6 and the time series monitored in the step 4 are respectively represented as p= (x) 1 ,x 2 ,...,x n ) And q= (y) 1 ,y 2 ,...,y n ) And calculating the Euclidean distance between the time sequence P and the time sequence Q, and carrying out similarity analysis on the time sequence P and the time sequence Q according to the Euclidean distance, wherein the Euclidean distance is expressed as:
the direction similarity analysis comprises the steps of projecting points on a time sequence P and a time sequence Q in a plane coordinate system, taking a line between each point on a curve formed by the time sequence P and the time sequence Q and an origin of a coordinate axis as a vector, calculating cosine of an included angle of the two vectors to be used for representing cosine similarity, calculating average cosine similarity of the time sequence P and the time sequence Q, and carrying out the direction similarity analysis of the time sequence P and the time sequence Q according to the average cosine similarity, wherein the cosine similarity is expressed as follows:
7. the method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 5, wherein the method comprises the following steps: in the step 7, the dynamic time warping distance analysis includes, assuming that the time series P obtained in the step 6 and the time series Q monitored in the step 4 are represented as p= (x) 1 ,x 2 ,...,x m ) And q= (y) 1 ,y 2 ,...,y n ) The distance matrix between two time series is expressed as A m×n ＝(a ij ) m×n Wherein a is ij Calculating by adopting Euclidean distance;
let the dynamic time-planned path be w= (W) 1 ,w 2 ,...,w n ) Calculating the DTW distance of the time sequence P obtained in the step 6 and the time sequence Q obtained in the step 4, and carrying out similarity analysis according to the DTW distance, wherein the DTW distance is expressed as:
8. the method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 5, wherein the method comprises the following steps: in the step 8, the preset requirement is that the numerical similarity requirement, the direction similarity requirement and the DTW similarity requirement are met at the same time;
let the actual monitoring data range be R, the said predetermined requirement is: if index S DE Satisfy S DE ＝D E R is less than or equal to 10 percent, and the time sequence P obtained in the step 6 and the time sequence Q obtained in the step 4 meet the numerical similarity requirement; a determination coefficient (R is set for the time series curve of the actual monitoring data 2 ) A fitting curve larger than 0.98, calculating the DTW distance DTW between the time sequence Q of the actual monitoring data and the fitting curve 1 Calculating the DTW distance DTW between the time sequence P of the actual monitoring data and the time sequence P in the step 6 2 If the DTW is satisfied 2 ≤DTW 1 And (3) the time sequence P obtained in the step (6) and the time sequence Q obtained in the step (4) meet the DWT similarity requirement.
9. The method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 4, wherein the method comprises the following steps: in the step 8, the time series data of the monitoring data of the water level, the earth surface displacement, the deep displacement and the stress are added with the acquisition frequency according to the requirement of the landslide machine learning prediction model.
10. The method for improving landslide displacement prediction accuracy based on numerical simulation technology according to claim 5, wherein the method comprises the following steps: in the step 8, the time span of monitoring data acquisition of water level, ground surface displacement, deep displacement and stress is increased according to the displacement prediction of the potential risk of the target landslide.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211242391.9A CN115455791B (en) | 2022-10-11 | 2022-10-11 | Method for improving landslide displacement prediction accuracy based on numerical simulation technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211242391.9A CN115455791B (en) | 2022-10-11 | 2022-10-11 | Method for improving landslide displacement prediction accuracy based on numerical simulation technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115455791A CN115455791A (en) | 2022-12-09 |
| CN115455791B true CN115455791B (en) | 2024-02-02 |
Family
ID=84309246
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211242391.9A Active CN115455791B (en) | 2022-10-11 | 2022-10-11 | Method for improving landslide displacement prediction accuracy based on numerical simulation technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115455791B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116739184B (en) * | 2023-08-08 | 2023-11-07 | 四川川核地质工程有限公司 | Landslide prediction method and system |
| CN118310472B (en) * | 2024-06-07 | 2024-08-27 | 中汽建工(洛阳)检测有限公司 | Nuclear power peripheral high slope deformation monitoring system and method based on multi-source heterogeneous data |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110837669A (en) * | 2019-10-25 | 2020-02-25 | 中国地质大学（武汉） | Landslide uncertain model dynamic construction method based on multi-source heterogeneous data fusion |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10536616B2 (en) * | 2017-08-31 | 2020-01-14 | Canon Kabushiki Kaisha | Image pickup apparatus |
-
2022
- 2022-10-11 CN CN202211242391.9A patent/CN115455791B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110837669A (en) * | 2019-10-25 | 2020-02-25 | 中国地质大学（武汉） | Landslide uncertain model dynamic construction method based on multi-source heterogeneous data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115455791A (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115455791B (en) | Method for improving landslide displacement prediction accuracy based on numerical simulation technology | |
| CN115640996B (en) | Assessment method for water-rich complex stratum tunnel gushing water disaster | |
| CN108256172B (en) | Dangerous case early warning and forecasting method in process of pipe jacking and downward passing existing box culvert | |
| CN107368463B (en) | Roadway nonlinear deformation prediction method based on fiber bragg grating sensor network data | |
| CN104989456A (en) | Large-span underground engineering surrounding rock excavation stability monitoring and early warning method | |
| CN114048790B (en) | Road base strain analysis method based on coupling bidirectional LSTM and convolution structure network | |
| CN113267814B (en) | Method and device for measuring and calculating field shear wave velocity | |
| CN110705179A (en) | Water guide crack belt height accurate prediction method and system based on fusion neural network | |
| CN118095813B (en) | Visual monitoring method and system for foundation settlement based on BIM technology | |
| CN103853144B (en) | Spot sensor fault detection method based on oil recovery creation data | |
| Arabameri et al. | Application of novel ensemble models and k-fold CV approaches for Land subsidence susceptibility modelling | |
| CN117386355A (en) | Method for predicting high-strength concrete well wall damage in deep buried soil layer | |
| CN118094147B (en) | Pipeline leakage positioning method based on variational modal decomposition and bidirectional long-short-term network | |
| CN109902265B (en) | Underground early warning method based on hidden Markov model | |
| CN116384627A (en) | Geological disaster evaluation method based on machine learning | |
| CN113190902B (en) | Prediction method and system for earth surface displacement caused by tunnel construction | |
| CN117711140A (en) | Tunnel water bursting disaster timing early warning method and system based on multi-source data fusion | |
| CN112084553B (en) | Surveying method for tunnel planning | |
| CN103953024A (en) | Method for identifying abnormal data automatically monitored by foundation pit | |
| CN115019476B (en) | Landslide space-time information monitoring and early warning method based on multi-source information fusion | |
| CN114066271A (en) | Tunnel water inrush disaster monitoring and management system | |
| CN114693151A (en) | Bridge pile foundation state diagnosis method based on distributed strain space correlation | |
| CN114330442A (en) | Pipeline strain characteristic classification calculation method and system based on K-nearest neighbor method | |
| CN113808370A (en) | Landslide-oriented multi-index coupling monitoring and early warning method | |
| CN118008479A (en) | Digital forecasting and early warning method for tunnel geological disasters in high-risk karst areas |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |